CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization

• URL: http://arxiv.org/abs/2407.10424v5
• Date: Sun, 11 May 2025 07:35:24 GMT
• Title: CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization
• Authors: Yang Zhao, Di Huang, Chongxiao Li, Pengwei Jin, Muxin Song, Yinan Xu, Ziyuan Nan, Mingju Gao, Tianyun Ma, Lei Qi, Yansong Pan, Zhenxing Zhang, Rui Zhang, Xishan Zhang, Zidong Du, Qi Guo, Xing Hu,
• Abstract summary: Traditional methods of adapting large language models for hardware design rely on synthetic HDL datasets.<n>We propose an efficient LLM fine-tuning pipeline for HDL generation that integrates a multi-level summarization data synthesis process with a novel Chat-FIM-Tag supervised fine-tuning method.
• Score: 32.462699328256384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The design flow of processors, particularly in hardware description languages (HDL) like Verilog and Chisel, is complex and costly. While recent advances in large language models (LLMs) have significantly improved coding tasks in software languages such as Python, their application in HDL generation remains limited due to the scarcity of high-quality HDL data. Traditional methods of adapting LLMs for hardware design rely on synthetic HDL datasets, which often suffer from low quality because even advanced LLMs like GPT perform poorly in the HDL domain. Moreover, these methods focus solely on chat tasks and the Verilog language, limiting their application scenarios. In this paper, we observe that: (1) HDL code collected from the real world is of higher quality than code generated by LLMs. (2) LLMs like GPT-3.5 excel in summarizing HDL code rather than generating it. (3) An explicit language tag can help LLMs better adapt to the target language when there is insufficient data. Based on these observations, we propose an efficient LLM fine-tuning pipeline for HDL generation that integrates a multi-level summarization data synthesis process with a novel Chat-FIM-Tag supervised fine-tuning method. The pipeline enhances the generation of HDL code from natural language descriptions and enables the handling of various tasks such as chat and infilling incomplete code. Utilizing this pipeline, we introduce CodeV, a series of HDL generation LLMs. Among them, CodeV-All not only possesses a more diverse range of language abilities, i.e. Verilog and Chisel, and a broader scope of tasks, i.e. Chat and fill-in-middle (FIM), but it also achieves performance on VerilogEval that is comparable to or even surpasses that of CodeV-Verilog fine-tuned on Verilog only, making them the first series of open-source LLMs designed for multi-scenario HDL generation.

Related papers

• Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization [4.7966941517322725]
  Large Language Models (LLMs) have become widely used across diverse NLP tasks and domains.<n>LLMs show promise for tasks like Register-Transfer Level (RTL) code generation and summarization.<n>We propose Chain-of-Descriptions (CoDes) to enhance the performance of LLMs for VHDL code generation and summarization tasks.
  arXiv  Detail & Related papers  (2025-07-16T15:05:30Z)
• DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model [13.532046953850902]
  We present DeepRTL, a unified representation model that excels in both Verilog understanding and generation. Based on CodeT5+, DeepRTL is fine-tuned on a comprehensive dataset that aligns Verilog code with rich, multi-level natural language descriptions. We introduce the first benchmark for Verilog understanding and take the initiative to apply embedding similarity and GPT Score to evaluate the models' understanding capabilities.
  arXiv  Detail & Related papers  (2025-02-20T11:07:55Z)
• Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis [14.458529723566379]
  Large language models (LLMs) can be employed for programming languages such as Python and C++.<n>This paper explores leveraging LLMs to generate High-Level Synthesis (HLS)-based hardware design.
  arXiv  Detail & Related papers  (2025-02-19T17:53:59Z)
• Enabling New HDLs with Agents [0.24578723416255746]
  Large Language Models (LLMs) based agents are transforming the programming language landscape.<n>This paper investigates the challenges and solutions of enabling LLMs for Hardware Description Languages (HDLs)<n>It introduces HDLAgent, an AI agent optimized for LLMs with limited knowledge of various HDLs.
  arXiv  Detail & Related papers  (2024-12-31T20:37:20Z)
• HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design [55.54477725000291]
  HiVeGen is a hierarchical Verilog generation framework that decomposes generation tasks into hierarchical submodules. automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse. Real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.
  arXiv  Detail & Related papers  (2024-12-06T19:37:53Z)
• Crystal: Illuminating LLM Abilities on Language and Code [58.5467653736537]
  We propose a pretraining strategy to enhance the integration of natural language and coding capabilities. The resulting model, Crystal, demonstrates remarkable capabilities in both domains.
  arXiv  Detail & Related papers  (2024-11-06T10:28:46Z)
• Large Language Models as Code Executors: An Exploratory Study [29.545321608864295]
  This paper pioneers the exploration of Large Language Models (LLMs) as code executors. We are the first to examine this feasibility across various LLMs, including OpenAI's o1, GPT-4o, GPT-3.5, DeepSeek, and Qwen-Coder. We introduce an Iterative Instruction Prompting (IIP) technique that processes code snippets line by line, enhancing the accuracy of weaker models by an average of 7.22%.
  arXiv  Detail & Related papers  (2024-10-09T08:23:22Z)
• AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs [27.179391677757565]
  We develop AutoVCoder, a framework that significantly improves the correctness of generating Verilog code. Our framework integrates three novel techniques, including a high-quality hardware dataset generation approach. AutoVCoder shows a 0.5% and 2.2% improvement in functional correctness on the EvalMachine and EvalHuman benchmarks compared with BetterV.
  arXiv  Detail & Related papers  (2024-07-21T16:42:45Z)
• Case2Code: Scalable Synthetic Data for Code Generation [105.89741089673575]
  Large Language Models (LLMs) have shown outstanding breakthroughs in code generation.<n>Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs.<n>We propose a textbfCase2Code task by exploiting the expressiveness and correctness of programs.
  arXiv  Detail & Related papers  (2024-07-17T11:35:00Z)
• InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct [43.7550233177368]
  We propose INVERSE-INSTRUCT, which summarizes instructions from code snippets instead of the reverse. We present a series of code LLMs named InverseCoder, which surpasses the performance of the original code LLMs on a wide range of benchmarks.
  arXiv  Detail & Related papers  (2024-07-08T08:00:05Z)
• VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation [4.700008016247411]
  This paper introduces a comprehensive evaluation framework designed specifically for assessing VHDL code generation task. This dataset is constructed by translating a collection of Verilog evaluation problems to VHDL and aggregating publicly available VHDL problems, resulting in a total of 202 problems. To assess the functional correctness of the generated VHDL code, we utilize a curated set of self-verifying testbenches.
  arXiv  Detail & Related papers  (2024-06-06T00:06:50Z)
• A Multi-Expert Large Language Model Architecture for Verilog Code Generation [5.159745269633967]
  This paper introduces an innovative multi-expert LLM architecture for Verilog code generation (MEV-LLM) Our architecture uniquely integrates multiple LLMs, each specifically fine-tuned with a dataset that is categorized with respect to a distinct level of design complexity. Empirical evidence from experiments highlights notable improvements in terms of the percentage of generated Verilog outputs that are syntactically and functionally correct.
  arXiv  Detail & Related papers  (2024-04-11T16:58:29Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• HDLdebugger: Streamlining HDL debugging with Large Language Models [20.09481664579469]
  In the domain of chip design, Hardware Description Languages (HDLs) play a pivotal role. Despite the strong capabilities of Large Language Models (LLMs) in generating, completing, and inspecting software code, their utilization in the specialized field of HDL debug has been limited. We propose a framework, namely HDLger, which consists of HDL data generation via a reverse engineering approach, a search engine for retrieval-augmented generation, and a retrieval-augmented LLM fine-tuning approach. Our experiments, conducted on an HDL code dataset sourced from Huawei, reveal that HDLger outperforms 13 cutting
  arXiv  Detail & Related papers  (2024-03-18T11:19:37Z)
• Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework [50.02710905062184]
  This paper proposes an automated design-data augmentation framework, which generates high-volume and high-quality natural language aligned with Verilog and EDA scripts. The accuracy of Verilog generation surpasses that of the current state-of-the-art open-source Verilog generation model, increasing from 58.8% to 70.6% with the same benchmark.
  arXiv  Detail & Related papers  (2024-03-17T13:01:03Z)
• IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators [49.903001442804594]
  This work investigates the prospect of leveraging compiler intermediate representations (IR) to improve the multilingual capabilities of Code-LMs. We first compile SLTrans, a parallel dataset consisting of nearly 4M self-contained source code files. Next, we carry out continued causal language modelling training on SLTrans, forcing the Code-LMs to learn the IR language. Our resulting models, dubbed IRCoder, display sizeable and consistent gains across a wide variety of code generation tasks and metrics.
  arXiv  Detail & Related papers  (2024-03-06T17:52:08Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator [63.762209407570715]
  Genixer is a comprehensive data generation pipeline consisting of four key steps. A synthetic VQA-like dataset trained with LLaVA1.5 enhances performance on 10 out of 12 multimodal benchmarks. MLLMs trained with task-specific datasets can surpass GPT-4V in generating complex instruction tuning data.
  arXiv  Detail & Related papers  (2023-12-11T09:44:41Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• LEVER: Learning to Verify Language-to-Code Generation with Execution [64.36459105535]
  We propose LEVER, a simple approach to improve language-to-code generation by learning to verify the generated programs with their execution results. Specifically, we train verifiers to determine whether a program sampled from the LLMs is correct or not based on the natural language input, the program itself and its execution results. LEVER consistently improves over the base code LLMs(4.6% to 10.9% with code-davinci) and achieves new state-of-the-art results on all of them.
  arXiv  Detail & Related papers  (2023-02-16T18:23:22Z)
• Benchmarking Large Language Models for Automated Verilog RTL Code Generation [21.747037230069854]
  We characterize the ability of large language models (LLMs) to generate useful Verilog. We construct an evaluation framework comprising test-benches for functional analysis and a flow to test the syntax of Verilog code. Our findings show that across our problem scenarios, the fine-tuning results in LLMs more capable of producing syntactically correct code.
  arXiv  Detail & Related papers  (2022-12-13T16:34:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.